Determining object structure using physically mounted devices with only partial view of object

A non-transitory computer-readable medium having stored contents that cause one or more computing devices to perform automated operations including at least:

• acquiring, from multiple locations along a cable by a camera coupled to the cable, multiple images of an exterior of a pile of material that have visual data about a subset of the exterior of the pile of material and that do not provide visual coverage of one or more omitted surfaces of the exterior of the pile of material outside of the subset;
• generating and verifying, by the one or more computing devices, a three-dimensional (“3D”) computer model to represent the exterior of the pile of material for the indicated time, including:
• analyzing, by the one or more computing devices, the visual data of the multiple images to determine a shape at the indicated time of the subset of the exterior of the pile of material;
• predicting, by the one or more computing devices, one or more additional shapes at the indicated time of the one or more omitted surfaces of the exterior of the pile of material;
• combining, by the one or more computing devices, the determined shape of the subset of the exterior of the pile of material at the indicated time with the predicted one or more additional shapes of the one or more omitted surfaces at the indicated time to estimate a shape of the exterior of the pile of material for the 3D computer model;
• and
• verifying, by the one or more computing devices, the 3D computer model, including determining that one or more applied verification tests are satisfied for the 3D computer model;
• and
• providing, by the one or more computing devices, information about the 3D computer model for use on one or more client devices.

A system comprising:

• one or more hardware processors of one or more computing devices;
• and
• one or more memories with stored instructions that, when executed by at least one of the one or more hardware processors, cause the one or more computing devices to perform automated operations including at least:
• acquiring, from a physically mounted camera at a location and using multiple orientations from that location, multiple images of an exterior of a pile of material that have visual data about a subset of the exterior of the pile of material and that do not provide visual coverage of one or more omitted surfaces of the exterior of the pile of material outside of the subset;
• generating and verifying a three-dimensional (“3D”) computer model to represent the exterior of the pile of material for the indicated time, including:
• analyzing the visual data of the multiple images to determine a shape at the indicated time of the subset of the exterior of the pile of material;
• predicting one or more additional shapes at the indicated time of the one or more omitted surfaces of the exterior of the pile of material;
• combining the determined shape of the subset of the exterior of the pile of material at the indicated time with the predicted one or more additional shapes of the one or more omitted surfaces at the indicated time to estimate a shape of the exterior of the pile of material for the 3D computer model;
• and
• verifying the 3D computer model, including determining that one or more applied verification tests are satisfied for the 3D computer model;
• and
• providing information about the 3D computer model for use on one or more client devices.

A computer-implemented method comprising:

• acquiring, from one or more physically mounted sensors at one or more locations that include at least one depth-sensing device, one or more sensor readings of an exterior of a pile of material at an indicated time that have data about distance from the one or more locations to a subset of the exterior of the pile of material and that do not provide coverage of one or more omitted surfaces of the exterior of the pile of material outside of the subset;
• automatically generating and verifying, by one or more computing devices in response to the acquiring of the one or more sensor readings and without human intervention, a three-dimensional (“3D”) computer model to represent the exterior of the pile of material for the indicated time, including:
• analyzing, by the one or more computing devices, the data of the one or more sensor readings to determine a shape at the indicated time of the subset of the exterior of the pile of material;
• predicting, by the one or more computing devices, one or more additional shapes at the indicated time of the one or more omitted surfaces of the exterior of the pile of material;
• combining, by the one or more computing devices, the determined shape of the subset of the exterior of the pile of material at the indicated time with the predicted one or more additional shapes of the one or more omitted surfaces at the indicated time to estimate a shape of the exterior of the pile of material for the 3D computer model;
• and
• verifying, by the one or more computing devices, the 3D computer model, including determining that one or more applied verification tests are satisfied for the 3D computer model;
• and
• automatically providing, by the one or more computing devices and without human intervention, information about the 3D computer model for use on one or more client devices.